JP2023537390A - Systems and methods for processing electronic images to provide automatic routing of data - Google Patents

Abstract

A system and method for providing automatic routing of medical data is disclosed, comprising: identifying at least one rule corresponding to at least one condition and at least one recipient; and receiving medical data and associated medical metadata. determining whether the medical data, related medical metadata, and/or related artificial intelligence processing satisfy at least one condition of the at least one rule; and providing the medical data from the requesting institution to the at least one recipient upon determining that the requesting institution is satisfied. [Selection diagram] Figure 1C

Description

CROSS-REFERENCE TO RELATED APPLICATION(S) This application claims priority to U.S. Provisional Patent Application No. 63/064,714, filed Aug. 12, 2020, the entire disclosure of which is incorporated by reference in its entirety. shall be incorporated herein.

Various embodiments of the present disclosure relate generally to image processing methods. More specifically, certain embodiments of the present disclosure relate to systems and methods for automatically routing data based on image processing of tissue specimens.

Routing medical data to the correct set of recipients is critical for rapid and accurate diagnosis. For non-digitized medical data, it can be difficult to send samples to qualified professionals. For example, histopathology may require physical movement of the slide so that it can be reviewed by an expert. If the recommended specialist is outside the requesting hospital or clinic, there may be significant delays before the specialist receives the slides, or the non-recommended specialist may be required to contact the requesting institution. It may be chosen because of physical proximity. However, as more forms of medical data are digitized, they can be routed more efficiently to the best expert or set of experts for diagnosis and analysis. For example, in pathology, whole-slide images (WSI), a high-precision version of glass slides, can be digitally routed to expert sub-specialist pathologists for feedback and/or second opinions on cases. The same may apply to neurology (eg, electroencephalography) and radiology (eg, MRI or CT scans), and sub-specialist professionals may be called upon to perform definitive analysis of digital medical data. The techniques presented herein may be important in rare indications (eg, rare types of tumors) and other similar scenarios.

Diagnostic center workflow can be inefficient when medical data is routed to professionals who do not have sufficient expertise, which can lead to slow and costly patient diagnosis, or potential for misdiagnosis. can increase.

The background description provided herein is for the purpose of generally presenting the context of the present disclosure. It is an admission that, unless otherwise indicated herein, the material discussed in this section is not prior art to the claims of this application, and that inclusion in this section is prior art or suggestion of prior art. no.

According to certain aspects of the present disclosure, systems and methods for a medical data routing system are disclosed.

A computer-implemented method for providing automated routing of medical data comprises identifying at least one rule corresponding to at least one condition and at least one recipient; receiving medical data and associated medical metadata. and determining whether the medical data, the relevant medical metadata, and/or the relevant artificial intelligence process satisfy at least one condition of the at least one rule; and the at least one condition of the at least one rule is satisfied. providing the medical data from the requesting institution to the at least one recipient.

A computer system for providing automated routing of medical data comprises at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations, the operations comprising at least identifying at least one rule corresponding to a condition and at least one recipient; receiving medical data and associated medical metadata; medical data, associated medical metadata, and/or associated artificial intelligence; determining whether the processing satisfies at least one condition of the at least one rule; and, upon determining that the at least one condition of the at least one rule is satisfied, transmitting medical data from the requesting institution to at least one person. providing to a recipient.

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform actions for routing medical data, the actions satisfying at least one condition and at least one person. identifying at least one rule corresponding to a recipient; receiving medical data and related medical metadata; determining whether a condition is met; providing medical data from the requesting institution to at least one recipient upon determining that at least one condition of the at least one rule is met; including.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the disclosed embodiments as claimed.

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments and, together with the description, serve to explain the principles of the disclosed embodiments.

1 depicts an example block diagram of a system and network for medical data routing, according to an example embodiment of the present disclosure; FIG. 1 illustrates an example block diagram of a medical data evaluation platform, according to an example embodiment of the present disclosure; FIG. 1 depicts an example block diagram of a data evaluation tool, according to an example embodiment of the present disclosure; FIG. 4 illustrates an example method of training and using a medical data routing system, according to an example embodiment of the present disclosure; 1 illustrates an overview of an example embodiment execution workflow, according to an example embodiment of the present disclosure; 1 illustrates an overview of an example embodiment execution workflow, according to an example embodiment of the present disclosure; 1 illustrates an exemplary system that may implement the techniques presented herein.

Reference will now be made in detail to exemplary embodiments of the disclosure, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

The systems, devices, and methods disclosed herein will be described in detail by way of example with reference to the drawings. The examples described herein are merely examples and are provided to aid in explaining the apparatus, devices, systems, and methods described herein. Features or components shown in the drawings or discussed below are essential to any particular implementation of any of these devices, systems, or methods, unless otherwise specified as essential. should not be assumed to be.

Also, with respect to any described method, whether or not the method is described in conjunction with a flow diagram, unless the context dictates or requires otherwise, any explicit representation of the steps taken in performing the method It should be understood that neither explicit or implied ordering implies that these steps must be performed in the order presented, but instead may be performed in a different order or in parallel. .

As used herein, the term "exemplary" is used in the sense of "example" rather than "ideal." Furthermore, the terms "a" and "an" in this specification do not imply limitations in quantity, but rather the presence of one or more of the referenced item.

Artificial intelligence (AI) systems are becoming more widely used to evaluate medical data, but may fail to correctly process rarer conditions. If the AI system is in doubt, it can triage the case and send it to a qualified expert for diagnosis. One or more embodiments of the present disclosure may solve the above problems. For example, one or more embodiments may provide a method of systematically routing medical data to preferred professionals. Many areas of medicine could be improved by accelerating diagnostic time in areas where centers lack expertise.

The present disclosure relates to routing medical data to experts for evaluation based on a set of criteria, manual intervention, or AI-based evaluation of medical data. For example, the present disclosure relates to using AI or an established set of rules to route medical data to entities suitable for review, which may include diagnosis, treatment recommendations, or analysis. Medical data can be medical records (eg, text), medical images (eg, digital microscopy, whole slide images, X-ray scans, MRI scans, CT scans, etc.), genetic tests, genomic tests, and the like.

Exemplary embodiments may use a rule-based configuration file that communicates with a scanner/laboratory information system (LIS). Exemplary embodiments may be used in hospitals, animal hospitals, clinics, laboratories. Based on the configuration file, medical data can be transferred using a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.).

Improving the quality of digital medical data evaluation by qualified professionals can improve patient care, resulting in better diagnosis/treatment and reduced errors. In addition, turnaround time can be reduced because specialists can be automatically identified, so patients can receive diagnosis more quickly. Exemplary embodiments may be integrated with platforms used to display digital microscopy cases in either research or clinical environments (eg, hospitals or veterinary clinics).

One or more embodiments relate to a medical data routing system. Inputs to the system can be medical data and related information. Exemplary embodiments may be used with any form of medical data, including digitized pathology images such as whole slide images (WSI), still images, patient medical records, physician notes, radiological It may include, but is not limited to, scans, dental notes, and/or test results. Additionally, a set of recipients can be defined. The recipient can be a specific person within the requesting center, a department within the center, or an external entity (eg, an individual or group of individuals at another hospital or clinic).

FIG. 1A shows an exemplary block diagram of a system and network for routing medical data using machine learning, according to exemplary embodiments of the present disclosure.

Specifically, FIG. 1A shows an electronic network 120 that may be connected to servers such as hospitals, veterinary clinics, laboratories, and/or clinics. For example, physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information system 125, etc., may each, via one or more computers, servers, and/or handheld mobile devices, It may be connected to an electronic network 120 such as the Internet. According to an exemplary embodiment of the present application, electronic network 120 may also be connected to server system 110, which may include processing devices configured to implement medical data evaluation platform 100, According to an exemplary embodiment of the present application, the medical data evaluation platform 100 identifies specimen property information or image property information about medical data, and uses machine learning to identify routing information for the medical data. Includes assessment tool 101 .

Physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information system 125 refer to systems used by pathologists to review images of slides. In a hospital environment, tissue type information may be stored in laboratory information system 125 .

FIG. 1B shows an exemplary block diagram of a medical data evaluation platform 100 for routing medical data using machine learning. Medical data assessment platform 100 may include data assessment tool 101 , data ingest tool 102 , slide capture tool 103 , slide scanner 104 , slide manager 105 , storage 106 , laboratory information system 107 and viewing application tool 108 .

As described below, the data evaluation tool 101 refers to processes and systems for identifying data variable property information or health variable property information about digital pathology image(s). According to an exemplary embodiment, machine learning may be used to classify images.

The data ingest tool 102, according to an exemplary embodiment, transfers digital pathology images to various tools, modules, components, and devices used to classify and process digital pathology images. can promote.

According to an exemplary embodiment, slide capture tool 103 may scan pathology images and convert them to digital format. A slide may be scanned with a slide scanner 104 and a slide manager 105 may process the images on the slide to generate digitized pathology images and store the digitized images in storage 106 .

The display application tool 108 may provide the user with specimen property information or image property information regarding the digital pathology image(s), according to an exemplary embodiment. Information may be provided through various output interfaces (eg, screens, monitors, storage devices, and/or web browsers, etc.).

Data evaluation tool 101 and one or more of its components communicate via electronic network 120 to server system 110, physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information. Digitized slide images and/or patient information may be sent to and received from system 125 . Additionally, the server system 110 may include a storage device 109 to store data from at least one of the data evaluation tool 101 , data ingest tool 102 , slide capture tool 103 , slide scanner 104 , slide manager 105 , and display application tool 108 . Stores the received image and data. Server system 110 may also include processing devices for processing images and data stored in storage device 109 . Server system 110 may further include one or more machine learning tool(s) or functionality, eg, via a processing device. Alternatively or additionally, the present disclosure (or portions of the systems and methods of the present disclosure) may be executed on a local processing device (eg, laptop).

Any of the above devices, tools, and modules can be located on a device that can be connected to an electronic network, such as the Internet or a cloud service provider, via one or more computers, servers, and/or handheld mobile devices.

FIG. 1C shows an exemplary block diagram of data evaluation tool 101, according to an exemplary embodiment of the present disclosure. Data evaluation tool 101 may include training data platform 131 and/or subject data platform 135 .

According to one embodiment, training data platform 131 may include training data ingestion module 132 , data analysis module 133 , and routing identification module 134 .

According to one embodiment, training data platform 131 may create or receive training data that trains a machine learning model to effectively analyze and classify digital pathology images according to user-defined rules. used for For example, training data may be received from any one or any combination of server system 110, physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information system 125. can be The data used for training may come from real sources (eg, humans, animals, etc.) or from synthetic sources (eg, graphics rendering engines, 3D models, etc.). Examples of data include (a) digitized slides stained with various dyes such as (but not limited to) H&E, hematoxylin only, IHC, molecular pathology, and/or (b) 3D imaging such as microCT. tissue samples digitized from the device.

The training data capture module 132 may create or receive a dataset including one or more training datasets corresponding to digital pathology slides or other forms of medical data. For example, the training data set may be from any one or any combination of server system 110, physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information system 125, can be received. This data set can be kept on a digital storage device. The data analysis module 133 may identify quality control (QC) issues (eg, incompleteness) in the training dataset at a global or local level that may affect the usefulness of the dataset. For example, the quality score determination module may use information about the dataset as a whole, such as the dataset type, the overall quality of the sections of the specimen, the overall quality of the dataset itself, or the pathology slide characteristics, etc. can determine an overall quality score for The routing identification module 134 may analyze the medical data to determine whether the medical data satisfies rules set by the user. Determining whether medical data satisfies a rule and should then be routed to a recipient is important for rapid and accurate diagnosis.

According to one embodiment, target data platform 135 may include target data ingestion module 136 , routing analysis module 137 , and output interface 138 . The target data platform 135 may receive target data sets and apply machine learning models to the received target data to identify characteristics of the target data sets. For example, subject data may be received from one or any combination of server system 110, physician server 121, hospital server 122, clinical trial server 123, laboratory server 124, and/or laboratory information system 125. . The target data capture module 136 may receive a target data set corresponding to the target medical data set. The routing analysis module 137 may apply machine learning models to the target data set to identify characteristics of the target medical data set. For example, routing analysis module 137 may also apply a machine learning model to the target dataset to determine a quality score for the target dataset.

Output interface 138 may be used to output information regarding the target data and routing rules (eg, to a screen, monitor, storage device, web browser, etc.).

FIG. 2 illustrates an exemplary method of using machine learning to train and use a medical data routing system. According to one or more exemplary embodiments, rules are set such that if medical data meets certain criteria, the medical data can be routed to a predefined entity that reviews the medical data. Sets can be defined. Rules may be automatically executed or manually invoked by a user. For example, exemplary method 200 (eg, steps 201-205) and exemplary method 220 (eg, steps 221-229) may be performed by data evaluation tool 101 automatically or upon request from a user.

According to one embodiment, an exemplary method 200 for training a machine learning model to route medical data may include one or more of the following steps. At step 201, the method may include defining a training rule based on at least one condition for executing the training rule. A set of rules can be defined such that if a piece of medical data meets certain criteria, the medical data can be routed to a predefined entity that reviews the medical data. Rules may be automatically executed or manually invoked by a user. A requesting institution user (eg, an individual doctor, hospital, technician, administrator, etc.) may specify a set of conditions for executing a rule. The conditions are disease type, histology, sample site, the physician assigned to review the medical data at the requesting institution, and an AI that is incapable of making a diagnosis on the medical data with a sufficient level of certainty. It can be the output of the base system, and so on. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual or a group of individuals such as an entire medical department or company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.

At step 203, the method stores training medical data associated with at least one metadata component (e.g., tissue type, disease type, tissue site, etc.) on a digital storage device (e.g., hard drive, network drive, cloud storage, RAM, etc.).

At step 205, the method screens the training medical data to determine if the training medical data, its metadata, and/or associated processing meet at least one condition of the training rules. It can include training a learning model.

An exemplary method 220 of using the routing system may include one or more of the following steps. At step 221, the method may include defining a rule based on at least one condition for executing the rule. A set of rules can be defined such that if a piece of medical data meets certain criteria, the medical data can be routed to a predefined entity that reviews the medical data. Rules may be automatically executed or manually invoked by a user. A requesting institution user (eg, an individual doctor, hospital, technician, administrator, etc.) may specify a set of conditions for executing a rule. The conditions are disease type, histology, sample site, the physician assigned to review the medical data at the requesting institution, and an AI that is incapable of making a diagnosis on the medical data with a sufficient level of certainty. It can be the output of the base system, and so on. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual or a group of individuals such as an entire medical department or company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.

At step 223, the method stores the medical data associated with at least one relevant metadata component (e.g., tissue type, disease type, tissue site, etc.) on a digital storage device (e.g., hard drive, network drive, cloud storage, RAM, etc.).

At step 225, the method uses a machine learning model to screen medical data to determine if the medical data, its metadata, and/or associated processing meet at least one condition of a rule. can include

At step 227, the method may include routing the medical data to a recipient upon determining that the medical data matches the rule. Medical data, e.g., via the cloud, internet connection, and/or local area network, where the medical data, its metadata, and/or associated processing (e.g., by an AI-based system) meet criteria can be routed to a recipient or set of recipients specified in the . Activation of routing rules when a condition is met may be performed automatically or by a user, for example by clicking a button that triggers routing.

At step 229, the method may include returning the report generated by the recipient over the network to the requesting institution. After receiving the medical data from the requesting institution, the recipient may review the medical data, including automatically adding cases to the list of cases to be reviewed by an expert panel/consensus meeting. and scheduling any calendar events that may be requested, along with any video communications via plug-ins that may be required. After the recipient reviews the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

Exemplary embodiment: WSI of histopathological specimens
In many situations, pathologists working in medical centers may not have sufficient expertise to make a correct diagnosis. For example, where subspecialists such as dermatopathology are highly desired, or for rare or difficult-to-diagnose cancer histologies such as melanoma, there may be only a few pathologists in the world who are specialists in histology. In some cases, such a situation can occur. According to an exemplary embodiment, the input may be a collection of digital whole-slide images (WSI) of pathological specimens from a patient, which can be later routed to qualified professionals.
1. A rule for routing WSI may be defined as follows.
a. The user specifies category fields on which to run rules for WSI. The user can list the conditions that the WSI must meet for the rule to be executed, the condition being assigned to review the WSI at the disease type, tissue type, sample site, requesting institution. It could be a pathologist, the output of an AI-based system that is unable to make a diagnosis of WSI with a sufficient level of certainty, and the like.
b. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual pathologist or a group of pathologists, such as an entire medical department or an entire company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.
2. Pathology data is received in a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.) along with associated metadata such as tissue type, disease type, tissue site, and the like.
3. Medical data can be transferred, for example, via the cloud, internet connection, and/or local area network, to rule can be routed to a recipient or set of recipients specified in the . Activation of rules may be performed automatically, or may be done by a user, eg by clicking a button that triggers routing (see Figure 1).
4. The recipient will receive and review the data, including automatically adding the case to the list of cases to be reviewed by an expert panel/consensus meeting, and any calendaring that may be requested. Scheduling the event with any video communication via plug-ins that may be required may be included.
5. After the recipient(s) has reviewed the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

FIG. 3 shows an overview of an example embodiment execution workflow, according to an example embodiment of the present disclosure.

According to the exemplary embodiment shown in FIG. 3, workflow 30 (eg, steps 31-39) is performed by a pathologist in advance such that a set of digital pathology data is evaluated by an expert or group of experts. It may involve firing a specified rule, for example by clicking a button. After reviewing the data, the expert relays the review back to the requesting pathologist.

At step 31, a pathologist at the requesting institution may review medical data for the current patient or case. A pathologist may determine that an expert review is required, or a rule may determine that an expert review is required.

At step 33, a one-click expert relay may be initiated. When pathologists or rules determine that expert review is required, pathologists use one-click expert relay to send medical data to experts at another location or work space. obtain.

At step 35, the workflow may include automatic expert search and relay, so that pathologist users of the system do not have to manually find suitable experts and send medical data to another location.

At step 37, the workflow may include expert review and diagnosis based on the provided medical data.

At step 39, the workflow may include relaying the expert's reply to the requesting physician.

FIG. 4 shows an overview of execution workflow 40 of an exemplary embodiment of the present disclosure.

According to the exemplary embodiment shown in FIG. 4, an AI-based system automatically screens pathology data. If the AI-based system determines that the data cannot be diagnosed accurately (e.g., because it is a rare form of cancer), the data can be routed to an expert or group of experts for review, and then an expert may relay their views back to the requesting agency.

At step 41, the workflow may include scanning slides, which may be scanned into the system by slide scanner 104, and generating AI predictions from the system.

At step 43, the workflow may include determining that the AI prediction is uncertain or lacks expertise in the identified disease, such as rare cancer cases. A rule may be applied such that if a rare cancer is detected, the system recognizes that the AI prediction has high uncertainty.

At step 45, the workflow may include the system automatically searching for an expert and relaying the slide images to that expert if the AI module determines that the AI module lacks certainty or expertise.

At step 47, the workflow may include expert review of the relayed slide images and identifying diagnoses in the images.

At step 49, the workflow may include relaying the expert diagnosis back to the requesting location and physician.

At step 51, the workflow may include the requesting physician reviewing the expert diagnosis and deciding on a course of treatment.

Exemplary Embodiment: Radiology In many situations, radiologists working in medical centers may not have sufficient expertise to make a diagnosis. Such a situation can arise, for example, when a sub-specialist is essential, such as breast cancer. This can be significant in rare diseases or conditions for which there are only a few expert radiologists in the world. Inputs to the system are radiation scans from the patient and associated patient data. In radiology, rule-based routing applies to mammography, sonography, positron emission tomography (PET), magnetic resonance imaging (MRI), computed tomography (CT), fluoroscopy, bone density Scanning and/or dual energy X-ray absorptiometry (DXA) may be performed depending on the methodology. Routing may also be performed based on hardware manufacturer. Additionally, the digital radiographic images may be routed based on the radiologist's specialty, such as abdominal, breast, cardiac, musculoskeletal, thoracic, and/or neuroradiology. Urgent radiology samples may be automatically routed to an available radiologist or specialist radiologist for additional review. In dental radiology, in a dental office, dental x-rays can be routed to the correct subspecialty based on the dentist, patient history, and/or licensed dental assistant. Strict routing rules can be defined according to dental office requirements. In this embodiment, the input may be a collection of digital radiological data (eg, MRI scans, CT scans, X-ray scans, PET scans, etc.) from the patient and later routed to qualified professionals.

The steps of an exemplary embodiment of radiology may be as follows.
1. A rule for routing may be defined as follows.
a. The user specifies categorical fields on which to run rules on radiological data. A user may list conditions that radiological data may need to meet for a rule to be executed, such as disease type, tissue type, sample site, requesting institution to review radiological data. It may be the assigned pathologist, and/or the output of an AI-based system that the data cannot be diagnosed with a sufficient level of certainty. It may also be identified using the AI system that the center may have insufficient expertise on a given radiology scan, in which case the AI system may automatically perform the routing. For example, if the dental center lacks expertise in conditions such as osteopenia, abnormal wisdom teeth, cavities, infections, and/or cysts or tumors, scans (e.g., patient X-rays) can be automatically detected and routed to specialists within the medical center or outside the medical center.
b. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual radiologist or a group of radiologists, such as an entire medical department or an entire company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.
2. Radiation data is received in a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.) along with associated metadata such as tissue type, disease type, tissue site, and the like.
3. Radiation data, e.g., via the cloud, internet connection, and/or local area network, etc., can be transferred to the rules if the radiology data, its metadata, and/or associated processing (e.g., by an AI-based system) meets criteria. can be routed to a recipient or set of recipients specified in the . Activation of rules may be performed automatically or by a user, eg by clicking a button that causes routing.
4. The recipient will receive and review the data, including automatically adding the case to the list of cases to be reviewed by an expert panel/consensus meeting, and any calendaring that may be requested. Scheduling the event with any video communication via plug-ins that may be required may be included.
5. After the recipient(s) has reviewed the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

Exemplary Embodiment: Routing of Medical Records and Medical History In all areas of medicine, physicians can take notes and records in digitized text. In this embodiment, these records may be routed to qualified experts for review. Inputs to the system can be text-based medical data obtained from patients and related data. The input to this embodiment may be medical metadata, including some or all relevant documents, medical certificates, and laboratory results documents.

The steps of this embodiment may be as follows.
1. A rule for routing may be defined as follows.
a. Users (eg, individual doctors, hospitals, technicians, administrators, etc.) specify category fields for running rules on medical record data. Rules may be based on specific keywords, practitioners (trainees), tissue types, medical conditions, submitting clinicians, case IDs, accession numbers, and the like. Alternatively, AI systems can detect abnormal laboratory readings or other reporting information so that medical data can be automatically routed to specialists.
b. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual clinician or a group of clinicians, such as an entire medical department or an entire company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.
2. Receive medical data to a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.).
3. If the medical data, its metadata and/or associated processing (e.g. by an AI-based system) meet the criteria, the data can be regulated, e.g. It can be routed to a specified recipient or set of recipients. Activation of rules may be performed automatically or by a user, eg by clicking a button that causes routing.
4. The recipient will receive and review the data, including automatically adding the case to the list of cases to be reviewed by an expert panel/consensus meeting, and any calendaring that may be requested. Scheduling the event with any video communication via plug-ins that may be required may be included.
5. After the recipient(s) has reviewed the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

Exemplary Embodiment: Omics Data Genome sequencing of tumors and genetic testing of patients, including fetuses, is commonly performed to facilitate identification of mutations of concern. However, for rarer mutations, centers may not have sufficient expertise to understand the results of these assays. This embodiment routes this data to experts who have the necessary expertise to interpret the results of genetic or genomic assays. Using this embodiment, a digital case (including all relevant genetic information) can be identified by accession number, case ID, mutation, microsatellite instability, copy number variation, gene expression, methylation status, methods (total Based on genome sequence, RNA-seq, 16s microbiome sequence, bisulfite sequence), subtype, and/or submitting clinician, it can be routed to the correct subspecialty or clinician geneticist. In medical genetics and medical genomics, in hospitals, digital cases (including all relevant genetic information) can be routed to the correct subspecialty or clinical geneticist based on genetic or genomic data. Strict routing rules can be defined according to hospital requirements. An individual clinical geneticist may also consider the occurrence of specific conditions such as rare mutations, the presence of specific coding and non-coding genes, or the presence of intergenic and intronic single nucleotide polymorphisms. A set of rules can be set up to route cases and receive notifications.

The steps of this embodiment may be as follows.
1. A rule for routing may be defined as follows.
a. Users (eg, individual physicians/genetics, hospitals, vets, technicians, administrators, etc.) specify category fields for running rules on medical data. Rules can be based on specific tissue types, mutations, microsatellite instability, copy number variations, gene expression, methylation status, disease states, and the like. Alternatively, AI systems can detect aberrant genetic or genomic patterns, whereby medical data can be automatically routed to experts.
b. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual (physician or geneticist) or a group of individuals (physician or geneticist), such as an entire medical department or an entire company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.
2. Receive medical data to a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.).
3. If the medical data, its metadata and/or associated processing (e.g. by an AI-based system) meet the criteria, the data can be regulated, e.g. It can be routed to a specified recipient or set of recipients. Activation of rules may be performed automatically or by a user, eg by clicking a button that causes routing.
4. The recipient will receive and review the data, including automatically adding the case to the list of cases to be reviewed by an expert panel/consensus meeting, and any calendaring that may be requested. Scheduling the event with any video communication via plug-ins that may be required may be included.
5. After the recipient(s) has reviewed the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

Exemplary Embodiment: Digital Microscopy To diagnose a number of diseases, a slide of a sample taken from a patient can be used to make a diagnosis or guide a treatment. For example, histology slides, cytology slides, fluorescence in situ and/or hybridization slides, etc. may be used. Using digital microscopy, these specimens can be converted into digital images and then reviewed by experts or AI systems. In this embodiment, the system receives digital microscopy image(s) as input and then routes the image(s) and associated patient data to entities suitable for further analysis, diagnosis, and/or treatment recommendation. . The input to this embodiment may be a collection of digital microscope images and related medical data.

The steps of this embodiment may be as follows.
1. A rule for routing may be defined as follows.
a. The user specifies categorical fields to run rules on digital microscopy data. Alternatively, if the AI module has a high level of uncertainty, or if the AI module detects difficult situations with respect to digital microscope images (e.g. unique Pap smears, uncertain viability of cells such as embryonic cells), Slides can be set to be automatically routed to experts.
b. For each rule, a set of recipients can be defined. The recipient may be an insider of the requesting institution or an outsider. A recipient may be an individual or a group of individuals, such as an entire medical department or an entire company. Recipients may be defined as having a particular skill set or expertise that enables them to receive and evaluate medical data.
2. Receive medical data to a digital storage device (eg, hard drive, network drive, cloud storage, RAM, etc.).
3. If the medical data, its metadata and/or associated processing (e.g. by an AI-based system) meet the criteria, the data can be regulated, e.g. It can be routed to a specified recipient or set of recipients. Activation of rules may be performed automatically or by a user, eg by clicking a button that causes routing.
4. The recipient will receive and review the data, including automatically adding the case to the list of cases to be reviewed by an expert panel/consensus meeting, and any calendaring that may be requested. Scheduling the event with any video communication via plug-ins that may be required may be included.
5. After the recipient(s) has reviewed the medical data, the recipient's report may be sent back to the requesting institution, such as via the cloud, internet connection, and/or local area network.

As shown in FIG. 5, device 500 may include central processing unit (CPU) 520 . CPU 520 may be any type of processor device including, for example, any type of special purpose or general purpose microprocessor device. As will be appreciated by those skilled in the art, CPU 520 may also be a single processor in a multicore/multiprocessor system operating alone, or a single processor in a cluster of computing devices operating in a cluster or server farm. CPU 520 may be connected to a communication infrastructure 510 such as a bus, message queue, network, or multi-core message passing scheme.

Device 500 may also include main memory 540 , such as random access memory (RAM), and may also include secondary memory 530 . Secondary memory 530, such as read only memory (ROM), may be, for example, a hard disk drive or a removable storage drive. Such removable storage drives may include, for example, floppy disk drives, magnetic tape drives, optical disk drives, or flash memory. The removable storage drive in this embodiment reads from and/or writes to the removable storage unit in well-known fashion. Removable storage may include floppy disks, magnetic tapes, optical disks, etc. that are read from and written to by removable storage drives. As will be appreciated by those skilled in the art, such removable storage units typically include computer usable storage media that store computer software and/or data.

In alternative implementations, secondary memory 530 may include similar means for allowing computer programs or other instructions to be loaded into device 500 . Examples of such means include program cartridges and cartridge interfaces (such as those included in video game devices), removable memory chips (such as EPROM or PROM) and associated sockets, and software and data transfer to device 500 from removable storage units. Other removable storage units and interfaces may be mentioned.

Device 500 may also include a communications interface (“COM”) 560 . Communication interface 560 allows software and data to be transferred between device 500 and external devices. Communication interface 560 may include a modem, network interface (such as an Ethernet card), communication port, or PCMCIA slots and cards, or the like. Software and data transferred via communication interface 560 may take the form of signals, which may be electronic, electromagnetic, optical, or other signals receivable by communication interface 560 . These signals may be provided to communication interface 560 via communication paths of device 500, which may be, for example, wires or cables, optical fibers, telephone lines, cellular telephone links, RF links, or other communication paths. It can be implemented using channels.

The hardware elements, operating systems, and programming languages of such devices are conventional in nature and are assumed to be sufficiently familiar to those skilled in the art. Device 500 may also include input and output ports 550 for connecting with input and output devices such as keyboards, mice, touch screens, monitors, displays, and the like. Of course, various server functions may be implemented in a distributed fashion on a number of similar platforms in order to spread the processing load. Alternatively, the server may be implemented by suitable programming of a single computer hardware platform.

Throughout this disclosure, references to components or modules generally refer to items that can be logically grouped together to perform a function or group of related functions. Like reference numbers are generally intended to refer to the same or similar components. Components and/or modules may be implemented in software, hardware or a combination of software and/or hardware.

The tools, modules and/or functions described above may be executed by one or more processors. A "storage" type medium may include any or all of tangible memory, such as a computer or processor, or associated modules of tangible memory, such as various semiconductor memories, tape drives, and disk drives, which may include software programming. can provide non-transitory storage at any time.

Software may be communicated via the Internet, cloud service providers, or other telecommunications networks. For example, communications may allow software to be loaded from one computer or processor to another computer or processor. As used herein, terms such as computer "readable medium" or machine "readable medium", unless limited to non-transitory tangible "storage" media, involve providing instructions to a processor for execution. Refers to any medium.

The foregoing general description is exemplary and explanatory only, and is not intended to limit the present disclosure. Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended that the specification and examples be considered as illustrative only.

Claims (20)

A computer-implemented method for providing automated routing of medical data, comprising:
identifying at least one rule corresponding to at least one condition and at least one recipient;
receiving medical data and related medical metadata;
determining whether the medical data, the relevant medical metadata, and/or the relevant artificial intelligence process satisfy the at least one condition of the at least one rule;
providing the medical data from a requesting institution to the at least one recipient upon determining that the at least one condition of the at least one rule has been met;
The computer-implemented method, comprising: receiving a report from the at least one recipient of the at least one rule in response to the provision;
2. The computer-implemented method of claim 1, further comprising: 2. The computer-implemented method of claim 1, wherein the relevant artificial intelligence processing comprises artificial intelligence-based evaluation of the medical data. providing said medical data to at least one professional when said artificial intelligence-based evaluation of said medical data determines that said medical data cannot be accurately diagnosed;
4. The computer-implemented method of claim 3, further comprising: 4. The computer-implemented method of claim 3, wherein the associated artificial intelligence process provides the medical data to at least one expert in response to detecting a lack of expertise at the requesting institution. The medical data includes at least one whole slide image, at least one still image, at least one patient medical record, at least one physician note, at least one radiological scan, at least one dental note, and/or at least one 2. The computer-implemented method of claim 1, comprising inspection results. The at least one condition includes at least one disease type, at least one tissue type, at least one sample site, and/or at least one person assigned to review the medical data at the requesting institution. 2. The computer-implemented method of claim 1, comprising a physician. The relevant medical metadata may include at least one medical disease type, at least one medical tissue type, at least one medical sample site, and/or at least one person assigned to review the medical data. 2. The computer-implemented method of claim 1, comprising a physician. A computer system for providing automated routing of medical data, said computer system comprising:
at least one memory storing instructions;
at least one processor configured to execute the instructions to perform operations;
wherein the operation comprises:
accessing said at least one memory and executing processor readable instructions, said processor readable instructions being executed by said at least one processor to perform a plurality of functions. and the plurality of functions include:
identifying at least one rule corresponding to at least one condition and at least one recipient;
receiving medical data and related medical metadata;
determining whether the medical data, the relevant medical metadata, and/or the relevant artificial intelligence process satisfy the at least one condition of the at least one rule;
providing the medical data from a requesting institution to the at least one recipient upon determining that the at least one condition of the at least one rule has been met;
The computer system comprising: The operation is
receiving a report from the at least one recipient of the at least one rule in response to the provision;
10. The computer system of claim 9, further comprising: 10. The computer system of claim 9, wherein the relevant artificial intelligence processing includes artificial intelligence-based evaluation of the medical data. providing said medical data to at least one professional when said artificial intelligence-based evaluation of said medical data determines that said medical data cannot be accurately diagnosed;
12. The computer system of claim 11, further comprising: 12. The computer system of claim 11, wherein the associated artificial intelligence process provides the medical data to at least one expert in response to detecting a lack of expertise at the requesting institution. The at least one condition includes at least one disease type, at least one tissue type, at least one sample site, and/or at least one person assigned to review the medical data at the requesting institution. 10. The computer system of claim 9, comprising a physician. The relevant medical metadata may include at least one medical disease type, at least one medical tissue type, at least one medical sample site, and/or at least one person assigned to review the medical data. 10. The computer system of claim 9, comprising a physician. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform acts to provide automated routing of medical data, the acts comprising:
identifying at least one rule corresponding to at least one condition and at least one recipient;
receiving medical data and related medical metadata;
determining whether the medical data, the relevant medical metadata, and/or the relevant artificial intelligence process satisfy the at least one condition of the at least one rule;
providing the medical data from a requesting institution to the at least one recipient upon determining that the at least one condition of the at least one rule has been met;
the non-transitory computer-readable medium comprising: receiving a report from the at least one recipient of the at least one rule in response to the provision;
17. The non-transitory computer-readable medium of claim 16, further comprising: 17. The non-transitory computer-readable medium of claim 16, wherein the relevant artificial intelligence processing includes artificial intelligence-based evaluation of the medical data. providing said medical data to at least one professional when said artificial intelligence-based evaluation of said medical data determines that said medical data cannot be accurately diagnosed;
19. The non-transitory computer-readable medium of claim 18, further comprising: 19. The non-transitory computer-readable medium of claim 18, wherein the associated artificial intelligence process provides the medical data to at least one expert in response to detecting a lack of expertise at the requesting institution.